Annotated datasets for automatic white balance (AWB) are used for the evaluation and, when necessary, the training, of AWB methods. Relying on such datasets requires awareness of the potential bias in their content and characteristics: some methods are designed to rely on the presence of particular elements, such as human skin, while other methods learn implicit relationships between image content and light properties from training data. The dependency on these relationships makes it fundamental to understand whether the available datasets are actually representative of common application scenarios, such as the presence of human subjects, the diversity of composition, or the illumination conditions. In this paper we overview the most common datasets for Automatic White Balance, including those for single as well as multiple illuminant estimation, providing a critical analysis on their characteristics. Furthermore, we identify a number of existing methods for single illuminant estimation, as a representative pool of approaches to the problem with various levels of complexity. We investigate how the performance of these correlate to the image content of common datasets.

Buzzelli, M., Zini, S., Bianco, S., Ciocca, G., Schettini, R., Tchobanou, M. (2023). Analysis of biases in automatic white balance datasets and methods. COLOR RESEARCH AND APPLICATION, 48(1 (January/February 2023)), 40-62 [10.1002/col.22822].

Analysis of biases in automatic white balance datasets and methods

Buzzelli, Marco
;
Zini, Simone;Bianco, Simone;Ciocca, Gianluigi;Schettini, Raimondo;
2023

Abstract

Annotated datasets for automatic white balance (AWB) are used for the evaluation and, when necessary, the training, of AWB methods. Relying on such datasets requires awareness of the potential bias in their content and characteristics: some methods are designed to rely on the presence of particular elements, such as human skin, while other methods learn implicit relationships between image content and light properties from training data. The dependency on these relationships makes it fundamental to understand whether the available datasets are actually representative of common application scenarios, such as the presence of human subjects, the diversity of composition, or the illumination conditions. In this paper we overview the most common datasets for Automatic White Balance, including those for single as well as multiple illuminant estimation, providing a critical analysis on their characteristics. Furthermore, we identify a number of existing methods for single illuminant estimation, as a representative pool of approaches to the problem with various levels of complexity. We investigate how the performance of these correlate to the image content of common datasets.
Articolo in rivista - Articolo scientifico
automatic white balance; color constancy; dataset analysis; illuminant estimation;
English
2-set-2022
2023
48
1 (January/February 2023)
40
62
open
Buzzelli, M., Zini, S., Bianco, S., Ciocca, G., Schettini, R., Tchobanou, M. (2023). Analysis of biases in automatic white balance datasets and methods. COLOR RESEARCH AND APPLICATION, 48(1 (January/February 2023)), 40-62 [10.1002/col.22822].
File in questo prodotto:
File Dimensione Formato  
Buzzelli-2023-Color Res Appl-VoR.pdf

accesso aperto

Descrizione: Research Article
Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Creative Commons
Dimensione 5.88 MB
Formato Adobe PDF
5.88 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/391631
Citazioni
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 5
Social impact